Multi-feature-fusion Chines-text classification method based on Attention neural network

Abstract

A solution of the invention discloses a multi-feature-fusion Chines-text classification method based on Attention neural network, and belongs to the field of natural language processing. In order to further improve accuracy of Chinese-text classification, the method fully exploits features of text data under three different sizes of convolution kernel granularity through fusing three CNN paths; interconnections among the text data are manifested through fusing an LSTM path; and in particular, relatively important data features are enabled to play a greater role in a Chinese-text class recognition process through merging a provided Attention algorithm model, and thus recognition ability of a model on Chinese text classes is improved. Experiment results show that compared with a CNN model, an LSTM structure model and a combined model of the two parts under the same experiment conditions, the model provided by the invention is significantly improved in Chinese-text classification accuracy, and can be better applied to the Chinese-text classification field with high requirements on the classification accuracy.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a multi-feature fusion Chinese text classification method based on Attention neural network. Background technique [0002] Chinese text classification is an important means to efficiently manage and mine massive Chinese text information on the Internet, and it is an important research direction in natural language processing. Since the 1990s, many researchers have begun to apply various statistical methods and machine learning methods to automatic text classification, such as support vector machine SVM, AdaBoost algorithm, naive Bayesian algorithm, KNN algorithm and Logistic regression, etc. In recent years, with the rapid development of deep learning and various neural network models, text classification methods based on deep learning have attracted close attention and research from academia and industry. Some typical neural network models, such as long short-term memo...

AI Technical Summary

Problems solved by technology

Existing research and applications have proved that LSTM (long-term short-term memory network) is suitable for learning the long-term dependencies between language units in sentences, and CNN (convolutional neural network) is suitable for learning local features of sentences, but the current research has not Fully combine the advantages of the three algorithms

Images